The following data is a regression model where the U.S. Department of Transportation has tried to relate the rate of fatal traffic accidents (per 1000 licenses) to the percentage of motorists under the age of 21. Data has been collected for 42 major cities in the United States.

SUMMARY OUTPUT
Regression Statistics
Multiple R	0.83938748
R Square	0.70457134
Adjusted R Square	0.69718562
Standard Error	0.58935028
Observations	42
ANOVA
	df	SS	MS	F
Regression	1	33.13441764	33.1344	95.3964
Residual	40	13.89335048	0.34733
Total	41	47.02776812
	Coefficients	Standard Error	t Stat	P-value
Intercept	-1.5974138	0.371671454	-4.2979	0.00010
Percent Under 21	0.28705317	0.029389769	9.76711	3.79E-9

1. What percentage of the variability in fatality rates can be attributed to variations in the percentage of motorists under the age of 21?

1. If a city had 10% of its motorists under the age of 21, how many fatalities should it expect for every 1000 licenses it issues?

1. Test the notion that the percentage of motorists under 21 does not impact the fatality rate, against the notion that it does impact the rate, using an a = .01.